Related papers: Can Predictive Filters Detect Gradually Ramping Fa…
Influenced by deep penetration of the new generation of information technology, power systems have gradually evolved into highly coupled cyber-physical systems (CPS). Among many possible power CPS network attacks, a false data injection…
Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…
LLM-integrated applications are vulnerable to prompt injection attacks, where an attacker contaminates the input to inject malicious instructions, causing the LLM to follow the attacker's intent instead of the original user's. Existing…
Cyber data attacks are the worst-case interacting bad data to power system state estimation and cannot be detected by existing bad data detectors. In this paper, we for the first time analyze the likelihood of cyber data attacks by…
Federated Learning (FL) is increasingly being adopted in military collaborations to develop Large Language Models (LLMs) while preserving data sovereignty. However, prompt injection attacks-malicious manipulations of input prompts-pose new…
Backdoor attacks pose a significant threat to the integrity and reliability of Artificial Intelligence (AI) models, enabling adversaries to manipulate model behavior by injecting poisoned data with hidden triggers. These attacks can lead to…
Consider a stochastic process being controlled across a communication channel. The control signal that is transmitted across the control channel can be replaced by a malicious attacker. The controller is allowed to implement any arbitrary…
This letter proposes a novel, fully distributed, transient-safe resilient secondary control strategies for AC microgrids, addressing unbounded false data injection (FDI) attacks on control input channels. Unlike existing methods that focus…
False data injection attacks (FDIAs) on smart inverters are a growing concern linked to increased renewable energy production. While data-based FDIA detection methods are also actively developed, we show that they remain vulnerable to…
In large-scale networks, communication links between nodes are easily injected with false data by adversaries. This paper proposes a novel security defense strategy from the perspective of attack detection scheduling to ensure the security…
Cyber-physical system (CPS) is the foundational backbone of modern critical infrastructures, so ensuring its security and resilience against cyber-attacks is of pivotal importance. This paper addresses the challenge of designing anomaly…
Security issues have gathered growing interest within the control systems community, as physical components and communication networks are increasingly vulnerable to cyber attacks. In this context, recent literature has studied increasingly…
Prompt injection attacks aim to contaminate the input data of an LLM to mislead it into completing an attacker-chosen task instead of the intended task. In many applications and agents, the input data originates from multiple sources, with…
Modern power systems have begun integrating synchrophasor technologies into part of daily operations. Given the amount of solutions offered and the maturity rate of application development it is not a matter of "if" but a matter of "when"…
Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions, because of their instruction-following capabilities and…
Cyber Physical Systems (cps) are deployed in many mission-critical settings, such as medical devices, autonomous vehicular systems and aircraft control management systems. As more and more CPS adopt Deep Neural Networks (Deep Neural Network…
This paper introduces a novel, fully distributed control framework for DC microgrids, enhancing resilience against exponentially unbounded false data injection (EU-FDI) attacks. Our framework features a consensus-based secondary control for…
Neural code generation systems have recently attracted increasing attention to improve developer productivity and speed up software development. Typically, these systems maintain a pre-trained neural model and make it available to general…
Fuzzy Rule Interpolation (FRI) methods can serve deducible (interpolated) conclusions even in case if some situations are not explicitly defined in a fuzzy rule based knowledge representation. This property can be beneficial in partial…
Recent advances in artificial intelligence have enabled the generation of large-scale, low-cost predictions with increasingly high fidelity. As a result, the primary challenge in statistical inference has shifted from data scarcity to data…